Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Pet

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    wik
    -0.07
    fr
    -0.07
    那
    -0.06
    mention
    -0.06
    яз
    -0.06
    FR
    -0.06
    مام
    -0.06
    “At
    -0.06
    Interesting
    -0.06
    "At
    -0.06
    POSITIVE LOGITS
    ...(
    0.07
    (Packet
    0.07
    ела
    0.07
     webpack
    0.06
    <Rigidbody
    0.06
     '#
    0.06
    Fcn
    0.06
    ({...
    0.06
     listView
    0.06
     squeezed
    0.06
    Act Density 0.008%

    No Known Activations